

Article URL: https://lwn.net/SubscriberLink/1000485/670ef0045e5e8a3e/
Comments URL: https://news.ycombinator.com/item?id=42338134
Points: 56
# Comments: 45
Article URL: https://blog.kagi.com/kagi-teams
Comments URL: https://news.ycombinator.com/item?id=42339048
Points: 133
# Comments: 48

Nowadays, a common AI tech stack has hundreds of different prompts running across different LLMs.
Three key problems:
- Choices, picking from 100s of LLMs the best LLM for that 1 prompt is gonna be challenging, you're probably not picking the most optimized LLM for a prompt you wrote.
- Scaling/Upgrading, similar to choices but you want to keep consistency of your output even when models depreciate or configurations change.
- Prompt management is scary, if something works, you'll nev
Article URL: https://danwilkerson.com/posts/2024-12-04-square-zero
Comments URL: https://news.ycombinator.com/item?id=42318083
Points: 30
# Comments: 7

Article URL: https://hackerherald.com/
Comments URL: https://news.ycombinator.com/item?id=42338327
Points: 6
# Comments: 1

Article URL: https://blog.benjojo.co.uk/post/rfc-in-38-simple-steps
Comments URL: https://news.ycombinator.com/item?id=42327280
Points: 98
# Comments: 24
